English
Related papers

Related papers: Towards Understanding Continual Factual Knowledge …

200 papers

Knowledge distillation has been successfully applied to Continual Learning Named Entity Recognition (CLNER) tasks, by using a teacher model trained on old-class data to distill old-class entities present in new-class data as a form of…

Computation and Language · Computer Science 2025-08-12 Zhe Ren

Post-training, particularly reinforcement learning (RL) using self-play-generated data, has become a new learning paradigm for large language models (LLMs). However, scaling RL to develop a general reasoner remains a research challenge, as…

Artificial Intelligence · Computer Science 2024-10-02 Tianlong Wang , Junzhe Chen , Xueting Han , Jing Bai

Continual Pre-training (CPT) serves as a fundamental approach for adapting foundation models to domain-specific applications. Scaling laws for pre-training define a power-law relationship between dataset size and the test loss of an LLM.…

Machine Learning · Computer Science 2025-12-29 Lei Liu , Hao Zhu , Yue Shen , Zhixuan Chu , Jian Wang , Jinjie Gu , Kui Ren

When handling streaming graphs, existing graph representation learning models encounter a catastrophic forgetting problem, where previously learned knowledge of these models is easily overwritten when learning with newly incoming graphs. In…

Machine Learning · Computer Science 2024-07-11 Yilun Liu , Ruihong Qiu , Yanran Tang , Hongzhi Yin , Zi Huang

Continual Learning (CL) aims to incrementally update a trained model on new tasks without forgetting the acquired knowledge of old ones. Existing CL methods usually reduce forgetting with task priors, \ie using task identity or a subset of…

Computer Vision and Pattern Recognition · Computer Science 2023-10-17 Tao Zhuo , Zhiyong Cheng , Hehe Fan , Mohan Kankanhalli

Meta continual learning algorithms seek to train a model when faced with similar tasks observed in a sequential manner. Despite promising methodological advancements, there is a lack of theoretical frameworks that enable analysis of…

Machine Learning · Computer Science 2020-10-12 R. Krishnan , Prasanna Balaprakash

Understanding how Transformer-based language models store and retrieve factual associations is critical for improving interpretability and enabling targeted model editing. Prior work, primarily on GPT-style models, has identified MLP…

Computation and Language · Computer Science 2025-09-11 Minyeong Choe , Haehyun Cho , Changho Seo , Hyunil Kim

Large Language Models (LLMs) are capable of recalling multilingual factual knowledge present in their pretraining data. However, most studies evaluate only the final model, leaving the development of factual recall and crosslingual…

Computation and Language · Computer Science 2025-10-08 Yihong Liu , Mingyang Wang , Amir Hossein Kargaran , Felicia Körner , Ercong Nie , Barbara Plank , François Yvon , Hinrich Schütze

Continual learning aims to sequentially learn new tasks without forgetting previous tasks' knowledge (catastrophic forgetting). One factor that can cause forgetting is the interference between the gradients on losses from different tasks.…

Computation and Language · Computer Science 2025-12-01 Xueying Bai , Jinghuan Shang , Yifan Sun , Niranjan Balasubramanian

To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as continual learning, provides a foundation for AI systems to…

Machine Learning · Computer Science 2024-02-07 Liyuan Wang , Xingxing Zhang , Hang Su , Jun Zhu

Large Language Models (LLMs) are proficient at retrieving single facts from extended contexts, yet they struggle with tasks requiring the simultaneous retrieval of multiple facts, especially during generation. This paper identifies a novel…

Computation and Language · Computer Science 2024-10-29 Jinlin Wang , Suyuchen Wang , Ziwen Xia , Sirui Hong , Yun Zhu , Bang Liu , Chenglin Wu

Continual learning (CL) aims to empower models to learn new tasks without forgetting previously acquired knowledge. Most prior works concentrate on the techniques of architectures, replay data, regularization, \etc. However, the category…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Bolin Ni , Hongbo Zhao , Chenghao Zhang , Ke Hu , Gaofeng Meng , Zhaoxiang Zhang , Shiming Xiang

Large language models (LLMs) can acquire new capabilities through fine-tuning, but continual adaptation often leads to catastrophic forgetting. We propose CRAFT, a continual learning framework that avoids updating model weights by instead…

Machine Learning · Computer Science 2026-05-11 Md Anwar Hossen , Fatema Siddika , Juan Pablo Munoz , Tanya Roosta , Ali Jannesari

The storage and recall of factual associations in auto-regressive transformer language models (LMs) have drawn a great deal of attention, inspiring knowledge editing by directly modifying the located model weights. Most editing works…

Computation and Language · Computer Science 2025-02-28 Xiyu Liu , Zhengxiao Liu , Naibin Gu , Zheng Lin , Wanli Ma , Ji Xiang , Weiping Wang

Continual learning studies agents that learn from streams of tasks without forgetting previous ones while adapting to new ones. Two recent continual-learning scenarios have opened new avenues of research. In meta-continual learning, the…

Continual learning (CL) aims to constantly learn new knowledge over time while avoiding catastrophic forgetting on old tasks. We focus on continual text classification under the class-incremental setting. Recent CL studies have identified…

Computation and Language · Computer Science 2023-10-11 Yifan Song , Peiyi Wang , Weimin Xiong , Dawei Zhu , Tianyu Liu , Zhifang Sui , Sujian Li

Knowledge Tracing (KT) is committed to capturing students' knowledge mastery from their historical interactions. Simulating students' memory states is a promising approach to enhance both the performance and interpretability of knowledge…

Machine Learning · Computer Science 2025-08-12 Mingrong Lin , Ke Deng , Zhengyang Wu , Zetao Zheng , Jie Li

Currently used semantic parsing systems deployed in voice assistants can require weeks to train. Datasets for these models often receive small and frequent updates, data patches. Each patch requires training a new model. To reduce training…

Computation and Language · Computer Science 2021-03-23 Vladislav Lialin , Rahul Goel , Andrey Simanovsky , Anna Rumshisky , Rushin Shah

Effective decision-making in the real world depends on memory that is both stable and adaptive: environments change over time, and agents must retain relevant information over long horizons while also updating or overwriting outdated…

Machine Learning · Computer Science 2026-01-22 Oleg Shchendrigin , Egor Cherepanov , Alexey K. Kovalev , Aleksandr I. Panov

Sample efficiency is a crucial property of language models with practical implications for training efficiency. In real-world text, information follows a long-tailed distribution. Yet, we expect models to learn and recall frequent and…

Computation and Language · Computer Science 2025-06-23 Daniel Christoph , Max Ploner , Patrick Haller , Alan Akbik